1. Review: Probability Random variables, events Axioms of probability Atomic events Joint and marginal probability distributions Conditional probability distributions Product rule, chain rule Independence and conditional independence

2. Bayesian inference, Naïve Bayes model http://xkcd.com/1236/

3. Bayes Rule The product rule gives us two ways to factor a joint probability: Therefore, Why is this useful? –Can update our beliefs about A based on evidence B P(A) is the prior and P(A|B) is the posterior –Key tool for probabilistic inference: can get diagnostic probability from causal probability E.g., P(Cavity = true | Toothache = true) from P(Toothache = true | Cavity = true) Rev. Thomas Bayes (1702-1761)

4. Bayes Rule example Marie is getting married tomorrow, at an outdoor ceremony in the desert. In recent years, it has rained only 5 days each year (5/365 = 0.014). Unfortunately, the weatherman has predicted rain for tomorrow. When it actually rains, the weatherman correctly forecasts rain 90% of the time. When it doesn't rain, he incorrectly forecasts rain 10% of the time. What is the probability that it will rain on Marie's wedding?

5. Bayes Rule example Marie is getting married tomorrow, at an outdoor ceremony in the desert. In recent years, it has rained only 5 days each year (5/365 = 0.014). Unfortunately, the weatherman has predicted rain for tomorrow. When it actually rains, the weatherman correctly forecasts rain 90% of the time. When it doesn't rain, he incorrectly forecasts rain 10% of the time. What is the probability that it will rain on Marie's wedding?

6. Law of total probability

7. Bayes Rule example Marie is getting married tomorrow, at an outdoor ceremony in the desert. In recent years, it has rained only 5 days each year (5/365 = 0.014). Unfortunately, the weatherman has predicted rain for tomorrow. When it actually rains, the weatherman correctly forecasts rain 90% of the time. When it doesn't rain, he incorrectly forecasts rain 10% of the time. What is the probability that it will rain on Marie's wedding?

8. Bayes rule: Example 1% of women at age forty who participate in routine screening have breast cancer. 80% of women with breast cancer will get positive mammographies. 9.6% of women without breast cancer will also get positive mammographies. A woman in this age group had a positive mammography in a routine screening. What is the probability that she actually has breast cancer?

9. https://xkcd.com/1132/ See also: https://xkcd.com/882/https://xkcd.com/882/

10. Probabilistic inference Suppose the agent has to make a decision about the value of an unobserved query variable X given some observed evidence variable(s) E = e –Partially observable, stochastic, episodic environment –Examples: X = {spam, not spam}, e = email message X = {zebra, giraffe, hippo}, e = image features

11. Bayesian decision theory Let x be the value predicted by the agent and x* be the true value of X. The agent has a loss function, which is 0 if x = x* and 1 otherwise Expected loss for predicting x: What is the estimate of X that minimizes the expected loss? –The one that has the greatest posterior probability P(x|e) –This is called the Maximum a Posteriori (MAP) decision

12. MAP decision Value x of X that has the highest posterior probability given the evidence E = e: Maximum likelihood (ML) decision: likelihood prior posterior

13. Naïve Bayes model Suppose we have many different types of observations (symptoms, features) E 1, …, E n that we want to use to obtain evidence about an underlying hypothesis X MAP decision: –If each feature E i can take on k values, how many entries are in the (conditional) joint probability table P(E 1, …, E n |X = x)?

14. Naïve Bayes model Suppose we have many different types of observations (symptoms, features) E 1, …, E n that we want to use to obtain evidence about an underlying hypothesis X MAP decision: We can make the simplifying assumption that the different features are conditionally independent given the hypothesis: –If each feature can take on k values, what is the complexity of storing the resulting distributions?

15. Naïve Bayes model Posterior: MAP decision: likelihood priorposterior

16. Case study: Text document classification MAP decision: assign a document to the class with the highest posterior P(class | document) Example: spam classification –Classify a message as spam if P(spam | message) > P(¬spam | message)

17. Case study: Text document classification MAP decision: assign a document to the class with the highest posterior P(class | document) We have P(class | document)  P(document | class)P(class) To enable classification, we need to be able to estimate the likelihoods P(document | class) for all classes and priors P(class)

18. Naïve Bayes Representation Goal: estimate likelihoods P(document | class) and priors P(class) Likelihood: bag of words representation –The document is a sequence of words (w 1, …, w n ) –The order of the words in the document is not important –Each word is conditionally independent of the others given document class

19. Naïve Bayes Representation Goal: estimate likelihoods P(document | class) and priors P(class) Likelihood: bag of words representation –The document is a sequence of words (w 1, …, w n ) –The order of the words in the document is not important –Each word is conditionally independent of the others given document class

20. Bag of words illustration US Presidential Speeches Tag Cloud http://chir.ag/projects/preztags/ http://chir.ag/projects/preztags/

21. Bag of words illustration US Presidential Speeches Tag Cloud http://chir.ag/projects/preztags/ http://chir.ag/projects/preztags/

22. Bag of words illustration US Presidential Speeches Tag Cloud http://chir.ag/projects/preztags/ http://chir.ag/projects/preztags/

23. Naïve Bayes Representation Goal: estimate likelihoods P(document | class) and P(class) Likelihood: bag of words representation –The document is a sequence of words (w 1, …, w n ) –The order of the words in the document is not important –Each word is conditionally independent of the others given document class –Thus, the problem is reduced to estimating marginal likelihoods of individual words P(w i | class)

24. Parameter estimation Model parameters: feature likelihoods P(word | class) and priors P(class) –How do we obtain the values of these parameters? spam: 0.33 ¬spam: 0.67 P(word | ¬spam)P(word | spam)prior

25. Parameter estimation Model parameters: feature likelihoods P(word | class) and priors P(class) –How do we obtain the values of these parameters? –Need training set of labeled samples from both classes –This is the maximum likelihood (ML) estimate, or estimate that maximizes the likelihood of the training data: P(word | class) = # of occurrences of this word in docs from this class total # of words in docs from this class d: index of training document, i: index of a word

26. Parameter estimation Parameter estimate: Parameter smoothing: dealing with words that were never seen or seen too few times –Laplacian smoothing: pretend you have seen every vocabulary word one more time than you actually did P(word | class) = # of occurrences of this word in docs from this class + 1 total # of words in docs from this class + V (V: total number of unique words) P(word | class) = # of occurrences of this word in docs from this class total # of words in docs from this class

27. Summary: Naïve Bayes for Document Classification Naïve Bayes model: assign the document to the class with the highest posterior Model parameters: P(class 1 ) … P(class K ) P(w 1 | class 1 ) P(w 2 | class 1 ) … P(w n | class 1 ) Likelihood of class 1 prior P(w 1 | class K ) P(w 2 | class K ) … P(w n | class K ) Likelihood of class K …

28. Prediction Learning and inference pipeline Training Labels Training Samples Training Learning Features Inference Test Sample Learned model

29. Review: Bayesian decision making Suppose the agent has to make decisions about the value of an unobserved query variable X based on the values of an observed evidence variable E Inference problem: given some evidence E = e, what is P(X | e)? Learning problem: estimate the parameters of the probabilistic model P(X | E) given a training sample {(x 1,e 1 ), …, (x n,e n )}